Face recognition from video

In spite of over two decades of intense research, illumination and pose invariance remain prohibitively challenging aspects of face recognition for most practical applications. The objective of this work is to recognize faces using video sequences both for training and recognition input, in a realistic, unconstrained setup in which lighting, pose and user motion pattern have a wide variability and face images are of low resolution. In particular there are three areas of novelty: (i) we show how a photometric model of image formation can be combined with a statistical model of generic face appearance variation, learnt offline, to generalize in the presence of extreme illumination changes; (ii) we use the smoothness of geodesically local appearance manifold structure and a robust same-identity likelihood to achieve invariance to unseen head poses; and (iii) we introduce an accurate video sequence "reillumination" algorithm to achieve robustness to face motion patterns in video. We describe a fully automatic recognition system based on the proposed method and an extensive evaluation on 171 individuals and over 1300 video sequences with extreme illumination, pose and head motion variation. On this challenging data set our system consistently demonstrated a nearly perfect recognition rate (over 99.7%), significantly outperforming state-of-the-art commercial software and methods from the literature. © Springer-Verlag Berlin Heidelberg 2006.

KLAIR: A virtual infant for spoken language acquisition research

Recent research into the acquisition of spoken language has stressed the importance of learning through embodied linguistic interaction with caregivers rather than through passive observation. However the necessity of interaction makes experimental work into the simulation of infant speech acquisition difficult because of the technical complexity of building real-time embodied systems. In this paper we present KLAIR: a software toolkit for building simulations of spoken language acquisition through interactions with a virtual infant. The main part of KLAIR is a sensori-motor server that supplies a client machine learning application with a virtual infant on screen that can see, hear and speak. By encapsulating the real-time complexities of audio and video processing within a server that will run on a modern PC, we hope that KLAIR will encourage and facilitate more experimental research into spoken language acquisition through interaction. Copyright © 2009 ISCA.

Development of a tool for rapidly assessing the implementation difficulty and emissions benefits of innovations

Consumer goods manufacturers aiming to reduce the environmental impact associated with their products commonly pursue incremental change strategies, but more radical approaches may be required if we are to address the challenges of sustainable consumption. One strategy to realize step change reductions is to prepare a portfolio of innovations providing different levels of impact reduction in exchange for different levels of organizational resource commitment. In this research a tool is developed to support this strategy, starting with the assumption that through brainstorming or other eco-innovation approaches, a long-list of candidate innovations has been created. The tool assesses the potential greenhouse gas benefit of an innovative option against the difficulty of its implementation. A simple greenhouse gas benefit assessment method based on streamlined LCA was used to analyze impact reduction potential, and a novel measure of implementation difficulty was developed. The predictions of implementation difficulty were compared against expert opinion, and showed similar results indicating the measure can be used sensibly to predict implementation difficulty. The assessment of the environmental gain versus implementation difficulty is visualized in a matrix, showing the trade-offs of several options. The tool is deliberately simple with scalar measures of CO 2 emissions benefits and implementation difficulty so tool users must remain aware of other potential environmental burdens besides greenhouse gases (e.g. water, waste). In addition, although relative life cycle emissions benefits of an option may be low, the absolute impact of an option can be high and there may be other co-benefits, which could justify higher levels of implementation difficulty. Different types of consumer products (e.g. household, personal care, foods) have been evaluated using the tool. Initial trials of the tool within Unilever demonstrate that the tool facilitates rapid evaluation of low-carbon innovations. © 2011 Elsevier Ltd. All rights reserved.

The evolution of information while building cross-domain models of a design: A video experiment

Models capturing the connectivity between different domains of a design, e.g. between components and functions, can provide a tool for tracing and analysing aspects of that design. In this paper, video experiments are used to explore the role of cross-domain modelling in building up information about a design. The experiments highlight that cross-domain modelling can be a useful tool to create and structure design information. Findings suggest that consideration of multiple domains encourages discussion during modelling, helps identify design aspects that might otherwise be overlooked, and can help promote consideration of alternative design options. Copyright © 2002-2012 The Design Society. All rights reserved.

Development of modelling method selection tool for health services management: From problem structuring methods to modelling and simulation methods

Background: There is an increasing recognition that modelling and simulation can assist in the process of designing health care policies, strategies and operations. However, the current use is limited and answers to questions such as what methods to use and when remain somewhat underdeveloped. Aim. The aim of this study is to provide a mechanism for decision makers in health services planning and management to compare a broad range of modelling and simulation methods so that they can better select and use them or better commission relevant modelling and simulation work. Methods. This paper proposes a modelling and simulation method comparison and selection tool developed from a comprehensive literature review, the research team's extensive expertise and inputs from potential users. Twenty-eight different methods were identified, characterised by their relevance to different application areas, project life cycle stages, types of output and levels of insight, and four input resources required (time, money, knowledge and data). Results: The characterisation is presented in matrix forms to allow quick comparison and selection. This paper also highlights significant knowledge gaps in the existing literature when assessing the applicability of particular approaches to health services management, where modelling and simulation skills are scarce let alone money and time. Conclusions: A modelling and simulation method comparison and selection tool is developed to assist with the selection of methods appropriate to supporting specific decision making processes. In particular it addresses the issue of which method is most appropriate to which specific health services management problem, what the user might expect to be obtained from the method, and what is required to use the method. In summary, we believe the tool adds value to the scarce existing literature on methods comparison and selection. © 2011 Jun et al.

Improvements to Concrete Column Detection in Live Video

The automated detection of structural elements (e.g. concrete columns) in visual data is useful in many construction and maintenance applications. The research in this area is under initial investigation. The authors previously presented a concrete column detection method that utilized boundary and color information as detection cues. However, the method is sensitive to parameter selection, which reduces its ability to robustly detect concrete columns in live videos. Compared against the previous method, the new method presented in this paper reduces the reliance of parameter settings mainly in three aspects. First, edges are located using color information. Secondly, the orientation information of edge points is considered in constructing column boundaries. Thirdly, an artificial neural network for concrete material classification is developed to replace concrete sample matching. The method is tested using live videos, and results are compared with the results obtained with the previous method to demonstrate the new method improvements.

Detection of Construction Workers in Video Frames for Automatic Initialization of Vision Trackers

Vision based tracking can provide the spatial location of construction entities such as equipment, workers, and materials in large scale, congested construction sites. It tracks entities in video streams by inferring their locations based on the entities’ visual features and motion histories. To initiate the process, it is necessary to determine the pixel areas corresponding to the construction entities to be tracked in the following consecutive video frames. In order to fully automate the process, an automated way of initialization is needed. This paper presents the method for construction worker detection which can automatically recognize and localize construction workers in video frames. The method first finds the foreground areas of moving objects using a background subtraction method. Within these foreground areas, construction workers are recognized based on the histogram of oriented gradients (HOG) and histogram of the HSV colors. HOG’s have proved to work effectively for detection of people, and the histogram of HSV colors helps differentiate between pedestrians and construction workers wearing safety vests. Preliminary experiments show that the proposed method has the potential to automate the initialization process of vision based tracking.